JMIR Medical Informatics · 2018 · 247 citations · 10 references
ComputingComputer ScienceCybersecurityComputer SecurityCryptographyMachine LearningCryptographic AlgorithmsData EncryptionData ProtectionData SecurityHomomorphic EncryptionPrivacy-preserving AnalyticsClassification ModelsLeast Squares ApproximationLogistic RegressionPackingPrivacy-preserving Machine LearningPrivacy-preserving Model TrainingSecure Machine LearningSecure Outsourcing Of Computation
Learning models without accessing raw data has long been a goal for privacy‑preserving machine learning; homomorphic encryption offers a promising but challenging approach to enable secure data outsourcing on commercial clouds. This study aims to extend homomorphic encryption to support practical logistic regression models. The authors approximate the logistic function with least squares, introduce packing and parallelization techniques, and evaluate the approach on real datasets, showing feasible speed and memory usage. The model trains in about 116 minutes on the Edinburgh dataset, yields accurate predictions, and demonstrates that precision loss is negligible, establishing the first practical homomorphically encrypted logistic regression outsourcing model.
Learning a model without accessing raw data has been an intriguing idea to security and machine learning researchers for years. In an ideal setting, we want to encrypt sensitive data to store them on a commercial cloud and run certain analyses without ever decrypting the data to preserve privacy. Homomorphic encryption technique is a promising candidate for secure data outsourcing, but it is a very challenging task to support real-world machine learning tasks. Existing frameworks can only handle simplified cases with low-degree polynomials such as linear means classifier and linear discriminative analysis.The goal of this study is to provide a practical support to the mainstream learning models (eg, logistic regression).We adapted a novel homomorphic encryption scheme optimized for real numbers computation. We devised (1) the least squares approximation of the logistic function for accuracy and efficiency (ie, reduce computation cost) and (2) new packing and parallelization techniques.Using real-world datasets, we evaluated the performance of our model and demonstrated its feasibility in speed and memory consumption. For example, it took approximately 116 minutes to obtain the training model from the homomorphically encrypted Edinburgh dataset. In addition, it gives fairly accurate predictions on the testing dataset.We present the first homomorphically encrypted logistic regression outsourcing model based on the critical observation that the precision loss of classification models is sufficiently small so that the decision plan stays still.
10
Historical Development of the Newton–Raphson Method
Tjalling Ypma · SIAM Review · 1995 · 908 citations
Prognostic Modeling with Logistic Regression Analysis
Ewout W. Steyerberg, Marinus J.C. Eijkemans, Frank E. Harrell et al. · Medical Decision Making · 2001 · 544 citations